- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies joint training for visual place recognition (VPR) across heterogeneous environments. The authors observe that incorporating indoor training data improves indoor recognition but can degrade performance on some outdoor benchmarks. To address this issue, they propose SceneMoE-VPR, which replaces the shared adapter in a DINOv2-based side adaptation network with a heterogeneous mixture of experts. The module combines an always-active shared expert with four spatial experts selected through image-level Top-K routing. Experiments with three outdoor training datasets and one indoor dataset show consistent improvements over SelaVPR++ on four main benchmarks, increasing average R@1 from 88.9% to 89.5%.
Critical strengths
-
The paper addresses a practically relevant problem. Existing VPR models are often trained for particular environments, while real-world applications require reliable recognition across diverse scenes. The observed performance trade-off when adding indoor training data provides a concrete motivation for studying cross-environment adaptation.
-
The heterogeneous expert design is reasonably motivated by the spatial characteristics of VPR. Different operators are used to capture geometric variation, local structure, directional layout, and multi-scale context, while image-level routing allows different expert combinations for different inputs. Adapting a frozen pretrained backbone is also a practical design choice.
-
The experimental evaluation includes useful controlled comparisons and ablations. In particular, retraining SelaVPR++ under the same four-dataset setting makes the main comparison more meaningful. The paper also investigates individual experts, the shared branch, router inputs, and load balancing, with additional benchmarks reported in the appendix. These results provide useful empirical evidence for the proposed approach.
Critical weaknesses
-
The method appears to be a fairly incremental extension of SelaVPR++, with most components building on existing designs. While the heterogeneous MoE improves performance, the current ablations do not isolate the effects of expert heterogeneity, dynamic routing, and increased model capacity. Comparisons with homogeneous MoE and parameter-matched shared adapters are needed to establish the necessity of the proposed design.
-
The motivation regarding cross-environment interference is reasonable, but the empirical evidence is not particularly strong. Improvements over the shared adapter are modest, and performance on Nordland remains below the outdoor-only baseline. It is therefore unclear whether the proposed MoE genuinely alleviates cross-environment interference or simply provides a small gain through additional capacity.
-
The comparison with closely related methods is incomplete. In particular, QAA [1] and MegaLoc [2] also address multi-dataset training or general-purpose place retrieval, making them highly relevant baselines. The current comparisons involve different training configurations and do not clearly establish the advantage of heterogeneous MoE over existing approaches to generalizable VPR.
-
I am not fully convinced by the evidence for scene-adaptive specialization. Figure 4 shows routing patterns across datasets, but some layers exhibit similar selections, leaving it unclear whether routing meaningfully depends on individual images. Likewise, removing an expert and observing a performance drop does not establish that it has learned the specific geometric, directional, or multi-scale properties claimed by the authors.
[1] Query-based adaptive aggregation for multi-dataset joint training toward universal visual place recognition. ICRA.
[2] MegaLoc: One Retrieval to Place Them All. CVPR Workshops.
Questions for authors
-
The current ablations do not quite tell us whether the gains come from heterogeneous experts or simply from having more capacity. What happens if all experts use the same architecture, or if the routing is fixed? A comparison under similar parameter and computational budgets would make this much clearer.
-
I wonder whether the performance drop after adding ScanNet is necessarily caused by shared adaptation. Have you tried adjusting the sampling ratio or loss weight of the indoor data? It would be useful to know whether a simpler change to the training setup could alleviate the same issue.
-
QAA and MegaLoc seem particularly relevant to the problem studied here, yet neither appears in the main comparison. Is there a reason for leaving them out? Even if a fully controlled comparison is difficult, some discussion of their relative performance and training settings would help.
-
I am not sure how to interpret the routing patterns in Figure 4. Are these the most frequently selected experts across each dataset? More importantly, how much does the routing actually vary between images, especially different views of the same place? This seems important for understanding whether the router has learned meaningful input-dependent behavior.
-
One implementation detail is still unclear to me: how exactly are the shared and routed expert outputs combined, and what happens to the CLS token? I also could not find a clear comparison of parameter counts, FLOPs, or inference speed with SelaVPR++. These details would help assess the cost of the proposed changes.